Envisioning the Roomba as AI Resource: A Classroom and Laboratory Evaluation.

摘要

This paper investigates the suitability of iRobot’s Roomba as a low-cost robotic platform for use in AI research and education. Examining the sensing and actuation capabilities of the vacuum base led us to develop sensor and actuation models more accurate than those provided by the raw API. We validate these models with implementations of Monte Carlo Localization and FastSLAM, algorithms that suggest the Roomba’s viability for AI research. Classroom trials incorporated the Roomba into CS 1 and CS 2 courses in the Spring of 2006, and student feedback has been similarly promising for educational uses. While the platform has both benefits and drawbacks relative to similarly-priced alternatives, we conclude that the Roomba will interest many educators, especially those focusing on the computational facets of robotics or applications involving large, homogeneous groups of physical agents. for several resources now available to AI educators and researchers: • Classroom-tested, cross-platform drivers and support software for the Roomba • Sensor and actuation models that improve upon the published Roomba Open Interface serial API • Implementations of localization, mapping, and vision algorithms that have been tested on the Roomba Based on these resources and the perspective of the past year of use, we conclude that the Roomba is a promising alternative to the many other low-cost robot platforms available for research and education (Figure 2). As presented, the Roomba will interest practitioners whose focus lies in the computational and/or applied robotics.